|本期目录/Table of Contents|

[1]冯兴龙,吴田,万亚旭,等.基于人-物交互关系检测的带电作业人员行为识别方法研究*[J].中国安全生产科学技术,2024,20(9):208-211.[doi:10.11731/j.issn.1673-193x.2024.09.025]
　FENG Xinglong,WU Tian,WAN Yaxu,et al.Research on behavior recognition method of live working personnel based on human-object interaction detection[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2024,20(9):208-211.[doi:10.11731/j.issn.1673-193x.2024.09.025]
点击复制

基于人-物交互关系检测的带电作业人员行为识别方法研究*
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
20
期数:
2024年9期
页码:
208-211
栏目:
职业安全卫生管理与技术
出版日期:
2024-09-30

文章信息/Info

Title:
Research on behavior recognition method of live working personnel based on human-object interaction detection
文章编号:
1673-193X(2024)-09-0205-07
作者:
冯兴龙; 吴田; 万亚旭; 肖宾; 方春华; 黎鹏; 赵慧敏
（1.三峡大学 电气与新能源学院，湖北 宜昌 443002；
2.中国电力科学研究院有限公司，湖北 武汉 430074）
Author(s):
FENG Xinglong;  WU Tian;  WAN Yaxu;  XIAO Bin;  FANG Chunhua;  LI Peng;  ZHAO Huimin
(1.College of Electrical Engineering & New Energy,China Three Gorges University,Yichang Hubei 443002,China;
2.China Electric Power Research Institute,Wuhan Hubei 430074,China)
关键词:
带电作业; 人-物交互关系; 行为识别; ST-GCN; 骨架序列
Keywords:
live working;  human-object interaction;  behavior recognition;  ST-GCN;  skeleton sequence
分类号:
X934;X914
DOI:
10.11731/j.issn.1673-193x.2024.09.025
文献标志码:
A
摘要:
为解决现有视频行为识别方法难以区分带电作业过程中某些相似行为、可识别行为种类少、未高效利用人员与物品间交互关系等问题，提出1种基于人-物交互关系检测的配网带电作业人员行为识别方法。利用轻量化姿态估计算法识别人员骨架序列，然后通过时空图卷积网络(spatial temporal graph convolutional networks,ST-GCN)提取人体运动的时空间特征并进行初步分类。对于由骨骼姿态无法有效区分的相似行为，采用目标检测算法识别人员所用工器具及使用状态，并通过融合人体动作与作业工器具所含行为信息，实现视频行为的精确识别。研究结果表明：该方法能有效识别带电作业行为，对相似行为的识别准确率约为88.9%，相较于现有基于骨架序列的带电作业人员行为方法提升约53个百分点。研究结果可为提高现场安全管控水平提供参考思路。
Abstract:
In order to solve the problems that the existing video behavior recognition methods cannot distinguish some similar behavior in the process of live working,the number of identifiable types is small,and the interaction between personnel and objects is not utilized,a behavior recognition method of live working personnel in distribution network based on human-object interaction detection was proposed.Firstly,the lightweight pose estimation algorithm was used to identify the human skeleton sequence.Secondly,the spatio-temporal features of human motion were extracted and initially classified by the spatial temporal graph convolutional networks (ST-GCN).Finally,for the similar behavior that cannot be effectively distinguished by skeletal posture,the target detection algorithm was used to identify the tools used by the personnel and the state of use,and the accurate recognition of video behavior was realized by fusing the behavior information contained in human action and operation tools.The results show that the proposed method can effectively identify the live working behavior,and the recognition accuracy of similar behavior is about 88.9%,which is about 53% higher than that of the existing method based on skeleton sequence.The research results can provide reference ideas for improving the level of on-site safety management and control.

参考文献/References:

［1］崔铁军，郭大龙.基于改进YOLOX的变电站工人防护设备检测研究［J］.中国安全生产科学技术，2023，19(4)：201-206. CUI Tiejun，GUO Dalong.Research on detection of substation worker protective equipment based on improved YOLOX［J］.Journal of Safety Science and Technology，2023，19(4)：201-206.
［2］葛军凯，史令彬.现代科技在电力安全管理中的应用策略——评《电力安全风险管理》［J］.中国安全生产科学技术，2021，17(7)：191-191. GE Junkai，SHI Lingbin.Application strategy of modern technology in power safety management-review of “power safety risk management”［J］.Journal of Safety Science and Technology，2021，17(7)：191-191.
［3］余光凯,刘庭,刘凯,等.面向协作机械臂的10 kV配网带电作业安全距离研究及绝缘设计［J］.高电压技术,2023,49(9):3936-3945. YU Guangkai，LIU Ting，LIU Kai，et al.Research on safety distance and insulation design of 10 kV distribution line live working robot based on cooperative manipulator［J］.High Voltage Engineering,2023,49(9):3936-3945.
［4］常政威，彭倩，陈缨.基于机器学习和图像识别的电力作业现场安全监督方法［J］.中国电力，2020，53(4)：155-160. CHANG Zhengwei，PENG Qian，CHEN Ying.Safety supervision method for power operation site based on machine learning and image recognition［J］.Electric Power，2020，53(4)：155-160.
［5］王波，董礼，林勇，等.基于SENet-SSD的水电厂人员作业安全行为识别方法研究［J］.水电与新能源，2023，37(2)：26-29. WANG Bo，DONG Li，LIN Yong，et al.On the identification of safety operation behaviors of personnel in hydropower plants based on SENet-SSD［J］.Hydropower and New Energy，2023，37(2)：26-29.
［6］SONG L C，YU G，YUAN J S，et al.Human pose estimation and its application to action recognition：a survey［J］.Journal of Visual Communication and Image Representation，2021，76：103055.
［7］LINDEBERG T.Scale invariant feature transform［J］.Scholarpedia，2012，7(5)：10491.
［8］卢颖，吕希凡，郭良杰，等.基于Kinect的地铁乘客不安全行为识别方法与实验［J］.中国安全生产科学技术，2021，17(12)：162-168. LU Ying，LYU Xifan，GUO Liangjie，et al.Kinect-based recognition method and experiments on unsafe behavior of subway passengers［J］.Journal of Safety Science and Technology，2021，17(12)：162-168.
［9］赵小虎，黄程龙.基于Kinect的矿井人员违规行为识别算法研究［J］.湖南大学学报(自然科学版)，2020，47(4)：92-98. ZHAO Xiaohu，HUANG Chenglong.Research on identification algorithm of mine person’s violation behavior based on kinect［J］.Journal of Hunan University(Natural Sciences)，2020，47(4)：92-98.
［10］马双双，王佳，曹少中，等.基于深度学习的二维人体姿态估计算法综述［J］.计算机系统应用，2022，31(10)：36-43. MA Shuangshuang，WANG Jia，CAO Shaozhong，et al.Overview on two-dimensional human pose estimation methods based on deep learning［J］.Computer Systems & Applications，2022，31(10)：36-43.
［11］FANG H S，XIE S Q，TAI Y W，et al.Rmpe：regional multi-person pose estimation［C］//Proceedings of the 2017 IEEE International Conference on Computer Vision(ICCV).USA:IEEE，2017：2353-2362.
［12］CAO Z，HIDALGO G，SIMON T，et al.OpenPose：realtime multi-person 2d pose estimation using part affinity fields［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2021，43(1)：172-186.
［13］KE Q H，BENNAMOUN M，AN S J，et al.A new representation of skeleton sequences for 3D action recognition［C］//2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR)，USA:IEEE，2017：4570-4579.
［14］YAN S，XIONG Y，LIN D.Spatial temporal graph convolutional networks for skeleton-based action recognition［C］//32nd AAAI Conference on Artificial Intelligence (AAAI),2018：7444-7452.
［15］苏超，王国中.基于改进OpenPose的学生行为识别研究［J］.计算机应用研究，2021，38(10)：3183-3188. SU Chao，WANG Guozhong.Research on student behavior recognition based on improved OpenPose［J］.Application Research of Computers，2021，38(10)：3183-3188.
［16］LI S,FANG Z,SONG W F,et al.Bidirectional optimization coupled lightweight networks for efficient and robust multi-person 2D pose estimation［J］.Journal of Computer Science and Technology,2019,34:522-536.
［17］HOWARD A G，ZHU M L，CHEN B,et al.MobileNets：efficient convolutional neural networks for mobile vision applications［J］.International Journal of Computer Vision，2017,8（17）：12670695.
［18］孔玮，刘云，李辉，等.基于图卷积网络的行为识别方法综述［J］.控制与决策，2021，36(7)：1537-1546. KONG Wei，LIU Yun，LI Hui，et al.A survey of action recognition methods based on graph convolutional network［J］.Control and Decision，2021，36(7)：1537-1546.
［19］饶天荣，潘涛，徐会军.基于交叉注意力机制的煤矿井下不安全行为识别［J］.工矿自动化，2022，48(10)：48-54. RAO Tianrong，PAN Tao，XU Huijun.Unsafe action recognition in underground coal mine based on cross-attention mechanism［J］.Journal of Mine Automation，2022，48(10)：48-54.
［20］游越，伊力哈木·亚尔买买提.基于改进YOLOv5在电力巡检中的目标检测算法研究［J］.高压电器，2023，59(2)：89-96. YOU Yue，YILIHAMU Yaermaimaiti.Research on target detection algorithm based on improved YOLOv5 in power patrol inspection［J］.High Voltage Apparatus，2023，59(2)：89-96.
［21］HU J，SHEN L，ALBANIE S，et al.Squeeze-and-excitation networks［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，42(8)：2011-2023.
［22］张蔚澜，齐华，李胜.时空图卷积网络在人体异常行为识别中的应用［J］.计算机工程与应用，2022，58(12)：122-131. ZHANG Weilan，QI Hua，LI Sheng.Application of spatial temporal graph convolutional networks in human abnormal behavior recognition［J］.Computer Engineering and Applications，2022，58(12)：122-131.
［23］王超，徐楚昕，董杰，等.基于ST-GCN的空中交通管制员不安全行为识别［J］.中国安全科学学报，2023，33(5)：42-48. WANG Chao，XU Chuxin，DONG Jie，et al.Unsafe behavior recognition of air traffic controllers based on ST-GCN［J］.China Safety Science Journal，2023，33(5)：42-48.

相似文献/References:

[1]高玉坤,冯芊,王皖,等.10 kV带电作业风险评估模型构建与应用研究*[J].中国安全生产科学技术,2024,20(7):208.[doi:10.11731/j.issn.1673-193x.2024.07.028]
　GAO Yukun,FENG Qian,WANG Wan,et al.Research on construction and application of risk assessment model for 10kV live working[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2024,20(9):208.[doi:10.11731/j.issn.1673-193x.2024.07.028]

备注/Memo

备注/Memo:
收稿日期： 2024-05-21
* 基金项目： 国家自然科学基金项目(51807110)
作者简介： 冯兴龙，硕士研究生，主要研究方向为电网智能运检和带电作业技术。
通信作者： 吴田，博士，高级工程师，主要研究方向为电网智能运检和带电作业技术。
更新日期/Last Update: 2024-10-08